Learning Random Monotone DNF

14 years 27 days ago

Download www1.cs.columbia.edu

We give an algorithm that with high probability properly learns random monotone DNF with t(n) terms of length log t(n) under the uniform distribution on the Boolean cube {0, 1}n . For any function t(n) poly(n) the algorithm runs in time poly(n, 1/ ) and with high probability outputs an -accurate monotone DNF hypothesis. This is the first algorithm that can learn monotone DNF of arbitrary polynomial size in a reasonable average-case model of learning from random examples only. Our approach relies on the discovery and application of new Fourier properties of monotone functions which may be of independent interest.

Jeffrey C. Jackson, Homin K. Lee, Rocco A. Servedi

Real-time Traffic

Algorithms | APPROX 2008 | Monotone Dnf | Monotone Dnf Hypothesis | Random Monotone Dnf |

claim paper

» Learning Random Monotone DNF Under the Uniform Distribution

» On Learning Monotone DNF under Product Distributions

» Learning of Boolean Functions Using Support Vector Machines

» DNF Are Teachable in the Average Case

» Learning Monotone DNF from a Teacher That Almost Does Not Answer Membership Queries

» Mansours Conjecture is True for Random DNF Formulas

» Lower Bounds on Learning Random Structures with Statistical Queries

» Learning DNF from Random Walks

Post Info
More Details (n/a)

Added	12 Oct 2010
Updated	12 Oct 2010
Type	Conference
Year	2008
Where	APPROX
Authors	Jeffrey C. Jackson, Homin K. Lee, Rocco A. Servedio, Andrew Wan

Comments (0)

Sciweavers

Learning Random Monotone DNF

Algorithms | APPROX 2008 | Monotone Dnf | Monotone Dnf Hypothesis | Random Monotone Dnf |

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers